A method and device for constructing a three-dimensional scene for geological disaster emergency rescue drills

Through the drone collecting terrain data and combining BIM technology, a high-precision three-dimensional terrain model is established and a collapsed body model is generated, which solves the problems of inaccurate site selection and waste of land in the construction of traditional rescue drill scenes, and realizes high-precision and realistic rescue drill scene design and green and environmentally friendly earth and stone allocation.

CN120339537BActive Publication Date: 2025-08-19CHINA RAILWAY NO 2 ENG GROUP CO LTD +3
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202510823791.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-06-19
Publication Date
2025-08-19
Estimated Expiration
2045-06-19

AI Technical Summary

Technical Problem

The construction of traditional geological disaster emergency rescue drill scenarios has problems such as inaccurate site selection of drill scenarios, inaccurate disaster working conditions construction, and waste of land occupation.

Method used

Through drones, terrain point cloud data are collected, terrain models are established in combination with BIM technology, collapsed body models are generated, and rescue equipment models are planned. Mechanical fill is used to build geological disaster drill scenes, and EVA waterproof boards are used to protect railway structures to achieve high-precision three-dimensional scene construction.

Benefits of technology

It has achieved high three-dimensional terrain accuracy, realistic rescue drill scene design, accurate earth and stone allocation, and strong rescue guidance, achieving digital rescue scene design, modular equipment and informatization of command and control, and green and environmentally friendly.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120339537B_ABST
    Figure CN120339537B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of emergency rescue, and in particular to a method and device for constructing a three-dimensional scene for a geological disaster emergency rescue drill. The present invention establishes high-precision real-scene three-dimensional data through an unmanned aerial vehicle, establishes a landslide body model using BIM technology, and constructs a geological disaster drill scene on-site using mechanical filling. The engineering quantity of the engineering drill is accurately calculated, and the placement and location of rescue equipment are rationally planned and designed to ensure the smooth conduct of the engineering drill, thereby promoting the reserve of emergency rescue technology and the training of talents. Compared with the traditional rescue drill scene construction, this method has the following advantages: high three-dimensional terrain accuracy, realistic rescue drill scene design, accurate earthwork allocation, strong rescue drill guidance, and many other advantages, achieving the digitalization of rescue scene design, modularization of rescue equipment, informationization of command and control, and green and environmentally friendly construction of collapsed bodies.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of emergency rescue, and in particular to a method and equipment for constructing a three-dimensional scene for geological disaster emergency rescue drills. Background Art

[0002] Influenced by factors such as the geological environment and climate, natural disasters are frequent in Southwest my country, primarily landslides and collapses. Furthermore, tunnel collapses are more common in the southwest than in other regions due to the construction environment. Traditional rescue scenario construction, which relies on a flat design combined with rock and soil accumulation, presents challenges such as inaccurate scene selection, inaccurate construction of disaster scenarios, and wasted land.

[0003] Therefore, there is a need for a three-dimensional scene construction method for geological disaster emergency rescue drills that can be used to build engineering drill scenarios for geological disasters such as landslides and mud-rock flows in engineering drills, and can highly restore geological disaster conditions. Summary of the Invention

[0004] The purpose of the present invention is to overcome the problems of inaccurate site selection and disaster condition construction in the prior art, and waste of land, and to provide a method and equipment for constructing a three-dimensional scene for geological disaster emergency rescue drills.

[0005] In order to achieve the above-mentioned object of the invention, the present invention provides the following technical solutions:

[0006] A method for constructing a three-dimensional scene for geological disaster emergency rescue drills comprises the following steps:

[0007] S1: Data collection: Use drones to collect terrain point cloud data and real-scene 3D models of the exercise area;

[0008] S2: Establishing a three-dimensional terrain model: establishing a DEM model based on the terrain point cloud data, fusing the DEM model with the DOM model of the drill area and the real-scene three-dimensional model, and outputting a three-dimensional terrain model of the drill area;

[0009] S3: Establishing a collapse body model: generating a collapse body model in the three-dimensional terrain model according to the three-dimensional terrain model and preset collapse body parameters;

[0010] S4: Establish a rescue equipment model: select the corresponding preset rescue equipment group according to the current geological disaster type, and establish a BIM model of the rescue equipment group;

[0011] S5: Planning the rescue facility area: setting the rescue facility area in the three-dimensional terrain model, loading the BIM model of the rescue equipment group, and outputting the current three-dimensional terrain model as a three-dimensional scene model for geological disaster emergency rescue drills.

[0012] As a preferred embodiment of the present invention, S2 comprises the following steps:

[0013] S21: Classifying the terrain point cloud data once using a pre-trained AI classification module, and then performing secondary classification on the point cloud data of the unclassified area using an instance segmentation box, and outputting the result as a classified point cloud file;

[0014] S22: using TIN triangulation reconstruction + DEM optimization method to output the classified point cloud file as DEM data;

[0015] S23: Load the DEM data and the DOM model of the drill area through GIS software, and build a three-dimensional GIS model using raster data mapping;

[0016] S24: Loading the real-scene 3D model, fusing the real-scene 3D model with the 3D GIS model through a 3D data space coordinate high-reference alignment method, and outputting a 3D terrain model of the exercise area.

[0017] As a preferred solution of the present invention, the AI classification module performs model training through the labeled data set; wherein, the classification of point clouds includes one or more of ground point clouds, railway roadbed point clouds, vegetation point clouds below 2m, vegetation point clouds of 2m and above, tunnel portal wall point clouds and retaining wall point clouds.

[0018] As a preferred embodiment of the present invention, S3 comprises the following steps:

[0019] Obtaining the height and surface slope of the collapse body according to preset collapse body parameters; the collapse body parameters include simulated landslide points;

[0020] Bringing the height and surface slope of the collapsed body into the three-dimensional terrain model to obtain the bottom length of the accumulated body of the collapsed body;

[0021] A collapse body model is generated in the three-dimensional terrain model according to the height, surface slope and bottom length of the collapsed body, and the volume of the collapsed body model is obtained through the BIM entity of the collapsed body model.

[0022] As a preferred embodiment of the present invention, the bottom length of the accumulation body includes the bottom length of the accumulation body inside the tunnel and the bottom length of the accumulation body outside the tunnel;

[0023] Among them, the bottom length of the accumulation body in the tunnel = the height of the collapsed body / surface slope;

[0024] The bottom length of the accumulation outside the tunnel = the height of the tunnel entrance / the surface slope.

[0025] As a preferred embodiment of the present invention, the method further includes S6, comprising the following steps:

[0026] S6: constructing a drill scene: piling up the collapsed body according to the three-dimensional scene model outputted in S5;

[0027] Among them, the soil volume of the collapsed body = the volume of the collapsed body model.

[0028] As a preferred embodiment of the present invention, S6 comprises the following steps:

[0029] S61: Establish protection for tracks and tunnel inner walls: Lay at least one layer of EVA waterproof sheet on the inner wall of the tunnel lining and the railway subgrade to establish protection for the tracks and tunnel inner walls;

[0030] S62: Excavate soil in the drill area, and stack the collapsed bodies from bottom to top according to the three-dimensional scene model outputted in S5.

[0031] As a preferred embodiment of the present invention, the method further comprises cleaning up the collapsed body after completing the drill, comprising the following steps:

[0032] Cleaning the collapsed body by machinery;

[0033] When cleaning reaches the preset distance near the EVA waterproof board, switch to manual cleaning;

[0034] After the collapsed body is cleaned up, the EVA waterproof board is recovered and the cleaning work is completed.

[0035] As a preferred solution of the present invention, said S5 further includes a BIM coordinate conversion method;

[0036] Through the coordinate flipping method, the Y coordinate and Z coordinate of the BIM model are flipped at the same time to make the coordinate direction of the BIM model parallel to the coordinate direction of the GIS model.

[0037] An electronic device comprises at least one processor and a memory communicatively connected to the at least one processor; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute any of the methods described above.

[0038] Compared with the prior art, the present invention has the following beneficial effects:

[0039] This method uses drones to create high-precision real-world 3D data, employs BIM technology to create a landslide model, and employs mechanical fill to construct a geological disaster drill scenario. This accurately calculates the engineering workload for the drill and rationally plans and designs the placement of rescue equipment and locations, ensuring the smooth conduct of the drill and promoting the development of emergency rescue technology and personnel. Compared to traditional rescue drill scenario construction, this method offers numerous advantages, including high 3D terrain accuracy, realistic rescue drill scenario design, accurate earthwork allocation, and strong rescue drill guidance. It achieves digital rescue scenario design, modular rescue equipment, information-based command and control, and environmentally friendly collapse body construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 This is a flow chart of a method for constructing a three-dimensional scene for geological disaster emergency rescue drills according to Example 1 of the present invention;

[0041] Figure 2 This is a flow chart of a method for constructing a three-dimensional scene for geological disaster emergency rescue drills according to Example 3 of the present invention;

[0042] Figure 3 This is a schematic diagram of spatial geometric analysis of landslide points and bottom accumulation points in a method for constructing a three-dimensional scene for geological disaster emergency rescue drills according to Example 3 of the present invention;

[0043] Figure 4 This is a schematic diagram of laying EVA waterproof boards in a method for constructing a three-dimensional scene for geological disaster emergency rescue drills according to Example 3 of the present invention;

[0044] Figure 5 This is a schematic diagram of a rescue drill scene design in a method for constructing a three-dimensional scene for a geological disaster emergency rescue drill according to Example 3 of the present invention;

[0045] Figure 6 This is a structural schematic diagram of an electronic device described in Example 4 of the present invention, which utilizes the method for constructing a three-dimensional scene for geological disaster emergency rescue drills described in the previous embodiment.

[0046] Description of the accompanying drawings: 1-track, 2-tunnel portal wall, 3-eight-shaped wall, 4-EVA waterproof board, 5-collapsed body, 6-rescue facility area, 61-rescue equipment, 62-emergency rescue tent, 63-miniaturized rescue shield machine. DETAILED DESCRIPTION

[0047] The present invention will be further described in detail below in conjunction with test examples and specific embodiments. However, this should not be understood as limiting the scope of the present invention to the following embodiments, and all technologies implemented based on the present invention fall within the scope of the present invention.

[0048] Example 1

[0049] like Figure 1 As shown, a method for constructing a three-dimensional scene for geological disaster emergency rescue drills includes the following steps:

[0050] S1: Data collection: Use drones to collect terrain point cloud data and real-scene 3D models of the exercise area.

[0051] S2: Establishing a three-dimensional terrain model: establishing a DEM model based on the terrain point cloud data, fusing the DEM model with the DOM model of the drill area and the real-scene three-dimensional model, and outputting a three-dimensional terrain model of the drill area.

[0052] S3: Establishing a collapse body model: generating a collapse body model in the three-dimensional terrain model according to the three-dimensional terrain model and preset collapse body parameters.

[0053] S4: Establish a rescue equipment model: Select the corresponding preset rescue equipment group according to the current geological disaster type, and establish a BIM model of the rescue equipment group.

[0054] S5: Planning the rescue facility area: setting the rescue facility area in the three-dimensional terrain model, loading the BIM model of the rescue equipment group, and outputting the current three-dimensional terrain model as a three-dimensional scene model for geological disaster emergency rescue drills.

[0055] Example 2

[0056] This embodiment is a specific implementation of the method for constructing a three-dimensional scene for geological disaster emergency rescue drills described in Example 1, including the following steps:

[0057] S1: Data collection: Use drones to collect terrain point cloud data and real-scene 3D models of the exercise area.

[0058] S2: Establishing a three-dimensional terrain model: establishing a DEM model based on the terrain point cloud data, fusing the DEM model with the DOM model of the drill area and the real-scene three-dimensional model, and outputting a three-dimensional terrain model of the drill area.

[0059] S21: Classifying the terrain point cloud data once using a pre-trained AI classification module, and then performing secondary classification on the point cloud data of the unclassified area using an instance segmentation box, and outputting the result as a classified point cloud file;

[0060] The AI classification module performs model training using the labeled data set; wherein the point cloud classification includes one or more of ground point cloud, railway subgrade point cloud, vegetation point cloud below 2m, vegetation point cloud 2m and above, tunnel portal wall point cloud and retaining wall point cloud.

[0061] S22: using TIN triangulation reconstruction + DEM optimization method to output the classified point cloud file as DEM data;

[0062] S23: Load the DEM data and the DOM model of the drill area through GIS software, and build a three-dimensional GIS model using raster data mapping;

[0063] S24: Loading the real-scene 3D model, fusing the real-scene 3D model with the 3D GIS model through a 3D data space coordinate high-reference alignment method, and outputting a 3D terrain model of the exercise area.

[0064] S3: Establishing a collapse body model: generating a collapse body model in the three-dimensional terrain model according to the three-dimensional terrain model and preset collapse body parameters.

[0065] S31: obtaining the height and surface slope of the collapse body according to preset collapse body parameters; the collapse body parameters include simulated landslide points;

[0066] S32: Bringing the height and surface slope of the collapsed body into the three-dimensional terrain model to obtain the bottom length of the collapsed body;

[0067] The bottom length of the accumulation body includes the bottom length of the accumulation body inside the tunnel and the bottom length of the accumulation body outside the tunnel;

[0068] Among them, the bottom length of the accumulation body in the tunnel = the height of the collapsed body / surface slope;

[0069] The bottom length of the accumulation outside the tunnel = the height of the tunnel entrance / the surface slope.

[0070] S33: generating a collapse body model in the three-dimensional terrain model according to the height, surface slope and bottom length of the collapsed body, and obtaining the volume of the collapsed body model through the BIM entity of the collapsed body model.

[0071] S4: Establish a rescue equipment model: Select the corresponding preset rescue equipment group according to the current geological disaster type, and establish a BIM model of the rescue equipment group.

[0072] S5: Planning the rescue facility area: setting the rescue facility area in the three-dimensional terrain model, loading the BIM model of the rescue equipment group, and outputting the current three-dimensional terrain model as a three-dimensional scene model for geological disaster emergency rescue drills.

[0073] Furthermore, it also includes BIM coordinate conversion methods;

[0074] Through the coordinate flipping method, the Y coordinate and Z coordinate of the BIM model are flipped at the same time to make the coordinate direction of the BIM model parallel to the coordinate direction of the GIS model.

[0075] Furthermore, the method further includes S6, comprising the following steps:

[0076] S6: constructing a drill scene: piling up the collapsed body according to the three-dimensional scene model outputted in S5;

[0077] Among them, the soil volume of the collapsed body = the volume of the collapsed body model.

[0078] S61: Establish protection for tracks and tunnel inner walls: Lay at least one layer of EVA waterproof sheet on the inner wall of the tunnel lining and the railway subgrade to establish protection for the tracks and tunnel inner walls;

[0079] S62: Excavate soil in the drill area, and stack the collapsed bodies from bottom to top according to the three-dimensional scene model outputted in S5.

[0080] This embodiment uses EVA waterproof board, which can effectively prevent the collapse body from damaging the tunnel portal, lining, track, and roadbed structure, thereby ensuring the safe operation of the railway in the simulation drill; at the same time, it can also further improve the final efficiency of cleaning up the debris.

[0081] Furthermore, the method further includes cleaning up the collapsed body after completing the drill, including the following steps:

[0082] Cleaning the collapsed body by machinery;

[0083] When cleaning reaches the preset distance near the EVA waterproof board, switch to manual cleaning;

[0084] After the collapsed body is cleaned up, the EVA waterproof board is recovered and the cleaning work is completed.

[0085] Example 3

[0086] This embodiment is a specific application example of the method for constructing a three-dimensional scene for a geological disaster emergency rescue drill described in Example 2. Taking a sudden debris flow rescue drill at a railway tunnel entrance as an example, a three-dimensional scene is constructed. Figure 2 As shown, the following steps are included:

[0087] (1) UAV data collection

[0088] This operational railway geological disaster drill took place in Suifenhe City, Heilongjiang Province, nestled in a densely forested mountainous area. To accurately capture the actual terrain of the drill area, a DJI M350 drone equipped with a LiDAR system was first used to scan the terrain. Data was collected manually under flight control at an altitude of 50-60 meters. Point cloud data was collected in true color mode, with the highest point cloud density and three echoes. Beidou RTK positioning was used. After point cloud data collection was complete, the LiDAR module in DJI Zhitu software was used to stitch the point cloud data together, generating a dense point cloud of the original terrain in the LSA format.

[0089] To create detailed 3D real-world models of existing structures, including the railway subgrade, track 1, tunnel portal wall 2, and retaining wall splay 3, a DJI M4T drone with an optical imaging lens was used. Data was collected manually at an altitude of 50-60 meters. The image resolution was 40 million pixels, and positioning was performed using BeiDou RTK mode. The angle between the lens and the ground normal was 15 degrees. During data collection, the interval between shots was 3 seconds, ensuring an image overlap rate of at least 70% in the direction of the drone's flight and at least 75% in the direction of the drone's flight. For this, the lateral overlap rate = (coverage width of a single aerial image - drone altitude) / coverage width of a single aerial image > 75%. According to the M4T drone's lens specifications, the distance between two flight paths should be less than 45 meters when the drone is flying at an altitude of 50-60 meters. A 40-meter flight distance was used in this exercise, which improved the quality of the 3D model reconstruction of the aforementioned railway structures. After the aerial photographs are collected, DJI Zhitu’s optical image processing module is used to create a highly detailed 3D model of the real scene in OBJ format and a high-resolution digital orthophoto (DOM) in TIFF format through aerial triangulation.

[0090] (2) Establishing a three-dimensional terrain model

[0091] To accurately reproduce the terrain of the emergency rescue drill, a DEM, DOM, and real-world 3D model were fused, with the DOM being used. A real-world 3D model was used to represent the railway structure. Because this model contained redundant data such as vegetation and weeds, a highly detailed real-world 3D model of the railway structure was created using entity segmentation.

[0092] For the establishment of the DEM model, the LiDAR point cloud AI training classification is used for processing. The first step is to establish point cloud training samples. Through point cloud semantic segmentation, AI training sample files such as ground point cloud library, railway roadbed point cloud, vegetation library below 2m, vegetation library above 2m, tunnel portal wall point cloud, retaining wall point cloud, etc. are established respectively. After merging the samples into .onnx format files, the json language environment is selected to establish point cloud AI classification training samples. Then select the AI classification module, load the trained AI samples to classify the LiDAR point cloud, and for areas where the ground point classification is inaccurate, select the point cloud data of the area through instance segmentation for secondary classification. If it is still inaccurate, optimize the AI training samples until the ground point cloud data of each area has been accurately classified. Finally, the classified ground points are stored in a new point cloud file, and the TIN triangulation reconstruction + DEM optimization method is used to establish DEM data with a display resolution of 1m.

[0093] In the GIS software, the database is used to load DEM data and DOM images respectively, and a three-dimensional GIS model is established through raster data mapping. By loading the real-life three-dimensional model of the modified railway tunnel portal structure in the 3D-model mode, the three-dimensional data spatial coordinate high-datum alignment method is used to achieve the fusion of the real-life model and the GIS model, and establish a three-dimensional real terrain for emergency rescue disaster drills. The terrain restoration accuracy reaches more than 98%.

[0094] (3) Establishing a collapse model

[0095] The geological disaster condition of this patent is to simulate the landslide on the left side of the tunnel entrance, which leads to the burial of the tunnel entrance and part of the tunnel body. Figure 3 As shown in the figure, based on the spatial analysis of the real-scene model, the height difference between the simulated landslide point and the tunnel portal wall is calculated to be H=15.02m, the horizontal distance L=15.33m, the hypotenuse length M=21.46, and the slope α=44.4°. From this, the slope ratio of the simulated collapse surface can be deduced to be P=H / L=15.02 / 15.33=0.98:1. In engineering project construction, the slope of most temporary structures and mainline projects is 1:1. Therefore, the slope of the landslide surface in this project drill is an integer value of 1:1.

[0096] Using a BIM physical model, a collapse edge line N of arbitrary length was first established based on the topographical trends of the proposed collapse area. This edge line was then converted into a BIM physical model. Since the physical model and the 3D terrain model can be directly Boolean-operated, the BIM model's grading parameters were set to 1:1, with the grading length being greater than the aforementioned hypotenuse length M. Considering the presence of accumulation at the bottom of the collapse body and the need to restore the railway to its original state after the engineering drill, the simulated collapse body should be kept to a minimum. The real-life model measured the tunnel entrance's splayed wall length A1 = 7.2m, and the tunnel entrance height A2 = 6.4m. According to the on-site drill command center, the rescue escape route length A3 = 20m. By optimizing the collapse model, the resulting collapse body, when the top edge length was 7.5m, completely covered the tunnel entrance. The bottom length of the accumulation inside the tunnel was 10m, and the bottom length of the accumulation outside the tunnel was 14m.

[0097] Through BIM entity analysis, it can be calculated that the volume of the collapsed body is 565m³. On the right side of the tunnel entrance, there is an idle land with an area of 952m2. To solve the problem of the collapsed body's accumulation and filling, soil can be directly taken from this area with an average depth of 0.6m. Compared with the originally planned soil excavation location, the use of the real-life model + BIM collapse design method solved the problem of earthwork allocation of the collapsed body, shortened the soil excavation distance, avoided the problems of difficult and inefficient transportation of slag on railway tracks, and shortened the accumulation time of the collapsed body by 60%.

[0098] (4) Establish rescue equipment model

[0099] According to the railway collapse rescue drill plan, the equipment required for tunnel portal collapse rescue drills includes a split rescue drill, its supporting hydraulic station, its supporting generator set, small shield rescue equipment, a wheeled crane, and an excavator. Based on the geometric dimensions of the equipment, a 1:1 BIM model of the aforementioned rescue equipment was created using the BIM component library creation method, and each equipment model was saved as an OBJ format. To accommodate the storage of small supplies (water, food, charging boxes), as well as rest areas during on-site rescue drills, a 5m*6m multi-purpose tent was designed and also saved as an OBJ format.

[0100] (5) Planning rescue facility areas

[0101] On the three-dimensional terrain model of the collapsed body established above, the rescue equipment models were loaded separately in 3D-model mode. Since the coordinate Z direction of the BIM model corresponds to the coordinate Y direction of the GIS model, the loaded BIM model is perpendicular to the ground. Therefore, the coordinate flipping method is adopted to flip the Y and Z coordinates of the BIM model simultaneously to make the model coordinates parallel to the coordinate Z direction of the GIS model. Then, using the BIM entity assembly method, the equipment models were placed in the proposed parking area in sequence, with each rescue equipment placed at a distance of 2m. The tent was placed on the side close to the tunnel entrance, with a distance of 4m between it and the equipment.

[0102] (6) Constructing a practice scenario

[0103] The first is the protection of the track and the inner wall of the tunnel. In order to quickly restore the railway after the drill, the railway track, road foundation and track lining should be protected from damage by the collapsed body 5. Figure 4 As shown, a layer of EVA waterproof board 4 is laid on the inner wall of the tunnel lining and the railway roadbed, with a laying length of 15m inside the tunnel and 30m on the roadbed outside the tunnel. The overlap length between the horizontal and vertical directions of the drainage board is 15cm~20cm to prevent the slag from directly contacting the railway structure, thereby achieving the purpose of protecting the railway structure.

[0104] The second step is to pile up the collapsed body 5. Use an excavator and a loader to cooperate with each other, directly take soil (silty sand) from the vacant area on the right side of the tunnel entrance for accumulation, and pile up the collapsed body 5 from bottom to top. The height and slope of the accumulation body must be consistent with the parameters of the collapse model designed above.

[0105] Finally, the subject slogan board of the drill was set up. According to the requirements of the drill headquarters, a 2m high and 30m long subject drill slogan display stand was made on site on the retaining wall on the left side of the tunnel entrance using angle steel. The slogan was "Emergency rescue and reopening drill for collapsed railway tunnels". After the construction was completed, the drill scene was as follows: Figure 5 As shown, the rescue facility area 6 includes rescue equipment 61 and emergency disaster relief tents 62.

[0106] (7) Rescue drills

[0107] First, the exercise plan was activated. According to the requirements of the emergency mission exercise command, the impact of a geological disaster was simulated, resulting in the burial of the entrances at both ends of the railway tunnel and the collapse of water into the tunnel, causing 5 railway maintenance workers to be trapped inside the tunnel. The casualties were unknown and rescue was urgently needed. After receiving the order, the rescue team rushed to the scene as soon as possible and set up a cordon 500 meters around the tunnel entrance and exit.

[0108] The second is rescue environment detection, life detection, geological detection, and setting up an earthquake alarm system. The rescue team will work with an expert technical group to conduct a safety assessment of the collapsed slope, use drones, 3D laser scanners and other equipment for monitoring and measurement, and quickly establish a real-life 3D model of the disaster accident scene.

[0109] To further open up the life communication channel, the rescue team carried out drilling operations with a multifunctional fast drilling rig, and found the five trapped people. After the drilling rig penetrated the collapsed body 5, the rescuers locked the location of the trapped people with a multifunctional life detector, and then transported lighting, communications, food and medicine into the tunnel. The ventilation ducts continued to supply air into the tunnel space to ensure the life and health of the trapped people.

[0110] To further open up the rescue escape passage, a miniaturized rescue shield machine 63 with a diameter of 1m was used to quickly penetrate the collapsed body 5 and establish a rescue escape passage with a diameter of 1m.

[0111] Two rescue workers were further organized to immediately enter the rescue passage with portable stretcher protective gear and rescued the five trapped people one by one. The medical rescue personnel quickly took measures such as stopping bleeding and bandaging, and checked the health status of the trapped people.

[0112] (8) Cleaning up the collapsed body

[0113] After the rescue drill concluded, at the request of the rescue headquarters, an excavator and loader were used to quickly clear the collapsed mass 5 inside the tunnel and on the roadbed. When clearing the collapsed mass 5 near the tunnel lining, portal walls, and retaining walls, manual labor was used to slowly clean the collapsed mass 5 to prevent mechanical damage to the railway structure. After all collapsed mass 5 was cleared, the EVA waterproofing sheeting inside the railway roadbed and tunnel was rolled up and cleared, successfully completing the tunnel collapse rescue exercise.

[0114] Example 4

[0115] like Figure 6 As shown, an electronic device includes at least one processor, a memory communicatively connected to the at least one processor, and at least one input / output interface communicatively connected to the at least one processor; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method for constructing a three-dimensional scene for geological disaster emergency rescue drills described in the aforementioned embodiment. The input / output interface may include a display, a keyboard, a mouse, and a USB interface for inputting and outputting data.

[0116] Furthermore, the electronic device may be a desktop computer, a mobile phone, a tablet computer, a wearable electronic device, or the like that is capable of performing depth information recognition.

[0117] Furthermore, the processor may include one or more processing cores. The processor utilizes various interfaces and circuits to connect various components within the electronic device. It executes instructions, programs, code sets, or instruction sets stored in memory, and accesses data stored in memory to perform various functions and process data within the electronic device. Optionally, the processor can be implemented using at least one of the following hardware forms: a digital signal processing (DSP), a field-programmable gate array (FPGA), or a programmable logic array (PLA). The processor may integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU primarily handles the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing display content; and the modem handles wireless communications. It is understood that the modem may not be integrated into the processor and may be implemented separately via a communications chip.

[0118] The memory may include random access memory (RAM) or read-only memory (ROM). The memory may be used to store instructions, programs, codes, code sets, or instruction sets, such as the instructions or code sets used to implement a method for constructing a three-dimensional scene for a geological disaster emergency rescue drill provided in an embodiment of the present application. The memory may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for implementing at least one function, instructions for implementing each of the above-mentioned method embodiments, etc. The data storage area may also store data created by the electronic device during use (such as a mapping table of modulation sequence and depth, image data, and spectrum graph data).

[0119] Those skilled in the art will understand that all or part of the steps of the above-mentioned method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above-mentioned method embodiment; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM), magnetic disks or optical disks, and other media that can store program codes.

[0120] When the integrated unit described above is implemented as a software functional unit and sold or used as a standalone product, it can also be stored in a computer-readable storage medium containing program code that can be invoked by a processor to execute the methods described in the above-mentioned method embodiments. Based on this understanding, the technical solutions of the embodiments of the present invention, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product, stored in a storage medium, includes instructions for enabling a computer device (such as a personal computer, server, or network device) to execute all or part of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, hard disk, or ROM. Optionally, the computer-readable storage medium includes non-transitory computer-readable storage medium. The computer-readable storage medium has storage space for program code for executing any of the method steps described above. This program code can be read from or written to one or more computer program products. The program code can be compressed, for example, in a suitable form.

[0121] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for constructing a three-dimensional scene for geological disaster emergency rescue drills, characterized in that: The following steps are involved: S1: Data collection: Use drones to collect terrain point cloud data and real-scene 3D models of the exercise area; S2: Establishing a three-dimensional terrain model: establishing a DEM model based on the terrain point cloud data, fusing the DEM model with the DOM model of the drill area and the real-scene three-dimensional model, and outputting a three-dimensional terrain model of the drill area; S3: Establishing a collapse body model: generating a collapse body model in the three-dimensional terrain model according to the three-dimensional terrain model and preset collapse body parameters; S4: Establish a rescue equipment model: select the corresponding preset rescue equipment group according to the current geological disaster type, and establish a BIM model of the rescue equipment group; S5: Planning the rescue facility area: setting the rescue facility area in the three-dimensional terrain model, loading the BIM model of the rescue equipment group, and outputting the current three-dimensional terrain model as a three-dimensional scene model for geological disaster emergency rescue drills; Wherein, the S3 includes the following steps: Obtaining the height and surface slope of the collapse body according to preset collapse body parameters; the collapse body parameters include simulated landslide points; Bringing the height and surface slope of the collapsed body into the three-dimensional terrain model to obtain the bottom length of the accumulated body of the collapsed body; Generating a collapse body model in the three-dimensional terrain model according to the height, surface slope and bottom length of the collapse body, and obtaining the volume of the collapse body model through the BIM entity of the collapse body model; The bottom length of the accumulation body includes the bottom length of the accumulation body inside the tunnel and the bottom length of the accumulation body outside the tunnel; Among them, the bottom length of the accumulation body in the tunnel = the height of the collapsed body / surface slope; The bottom length of the accumulation outside the tunnel = the height of the tunnel entrance / the surface slope.

2. A method for constructing a three-dimensional scene for geological disaster emergency rescue drills according to claim 1, characterized in that: The S2 comprises the following steps: S21: Classifying the terrain point cloud data once using a pre-trained AI classification module, and then performing secondary classification on the point cloud data of the unclassified area using an instance segmentation box, and outputting the result as a classified point cloud file; S22: using TIN triangulation reconstruction + DEM optimization method to output the classified point cloud file as DEM data; S23: Load the DEM data and the DOM model of the drill area through GIS software, and build a three-dimensional GIS model using raster data mapping; S24: Loading the real-scene 3D model, fusing the real-scene 3D model with the 3D GIS model through a 3D data space coordinate high-reference alignment method, and outputting a 3D terrain model of the exercise area.

3. A method for constructing a three-dimensional scene for geological disaster emergency rescue drills according to claim 2, characterized in that: The AI classification module performs model training using the labeled data set; wherein the point cloud classification includes one or more of ground point cloud, railway subgrade point cloud, vegetation point cloud below 2m, vegetation point cloud 2m and above, tunnel portal wall point cloud and retaining wall point cloud.

4. The method for constructing a three-dimensional scene for geological disaster emergency rescue drills according to claim 1, characterized in that: The method further comprises S6, comprising the following steps: S6: constructing a drill scene: piling up the collapsed body according to the three-dimensional scene model outputted in S5; Among them, the soil volume of the collapsed body = the volume of the collapsed body model.

5. A method for constructing a three-dimensional scene for geological disaster emergency rescue drills according to claim 4, characterized in that: The S6 comprises the following steps: S61: Establish protection for tracks and tunnel inner walls: Lay at least one layer of EVA waterproof sheet on the inner wall of the tunnel lining and the railway subgrade to establish protection for the tracks and tunnel inner walls; S62: Excavate soil in the drill area, and stack the collapsed bodies from bottom to top according to the three-dimensional scene model outputted in S5.

6. A method for constructing a three-dimensional scene for geological disaster emergency rescue drills according to claim 5, characterized in that: The method further includes cleaning up the collapsed body after completing the drill, comprising the following steps: Cleaning the collapsed body by machinery; When cleaning reaches the preset distance near the EVA waterproof board, switch to manual cleaning; After the collapsed body is cleaned up, the EVA waterproof board is recovered and the cleaning work is completed.

7. The method for constructing a three-dimensional scene for geological disaster emergency rescue drills according to claim 1, characterized in that: Said S5 also includes a BIM coordinate conversion method; Through the coordinate flipping method, the Y coordinate and Z coordinate of the BIM model are flipped at the same time to make the coordinate direction of the BIM model parallel to the coordinate direction of the GIS model.

8. An electronic device, characterized in that: The invention comprises at least one processor and a memory communicatively connected to the at least one processor; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method according to any one of claims 1 to 7.

Citation Information

Patent Citations

  • Landslide body change detection method based on laser radar technology

    CN105242279A

  • Tunnel collapse rescue comprehensive exercise simulation system and application method

    CN107293179A